The Cases LJP Never Sees: Prosecution Decision Prediction for More Complete Criminal Liability Assessment
For legal AI researchers, this paper identifies and benchmarks a previously overlooked but critical stage of criminal liability assessment, revealing significant limitations of current LLMs in evidence evaluation and legal reasoning.
The paper introduces Prosecution Decision Prediction (PDP), a new Legal AI task that predicts prosecutorial decisions (prosecution or three types of non-prosecution) for cases before indictment, filling a blind spot in Legal Judgment Prediction (LJP). Experiments on a benchmark of 4,630 Chinese cases show that state-of-the-art LLMs perform substantially worse on PDP than on LJP, and standard enhancement methods fail to close the gap.
Legal Judgment Prediction (LJP) has become a core benchmark for evaluating AI in the criminal legal domain, but it only sees criminal cases that have already passed prosecutorial review and been formally indicted. As a result, LJP leaves a substantial blind spot in assessing criminal liability, overlooking cases involving insufficient evidence, no criminal liability, or guilt exempted from punishment. To fill this gap, we propose \textbf{Prosecution Decision Prediction (PDP)}, the first Legal AI task built around prosecutorial review, which classifies each case into prosecution or one of three non-prosecution decisions and reflects legal AI's capabilities in evidence evaluation, legal subsumption, and value-based discretion. We further construct \textbf{PDP-Bench}, a benchmark of 4{,}630 real Chinese prosecutorial decisions spanning 190 charges. Extensive experiments show that state-of-the-art LLMs perform substantially worse on PDP than on LJP and that mainstream enhancement routes fail to close the gap. Moreover, controlled RLVR interventions show that simple outcome rewards fail to produce generalizable PDP discrimination.